From memento
Analyzes markdown documentation files for redundancy by detecting repeated 2-5 word phrases, calculating percentage, and reporting top repeats. Use when reviewing generated docs for quality or before committing if >10% redundant.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memento:check-redundancyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyzes markdown files for redundant content by detecting repeated phrases and calculating redundancy percentage.
Analyzes markdown files for redundant content by detecting repeated phrases and calculating redundancy percentage.
Use this skill when:
From target project, run:
python ${CLAUDE_PLUGIN_ROOT}/skills/check-redundancy/scripts/check-redundancy.py <file>
(repeated occurrences - unique count) / total phrases × 1000: Optimal (≤10% redundancy)1: High redundancy (>10%, needs optimization)2: Errorpython ${CLAUDE_PLUGIN_ROOT}/skills/check-redundancy/scripts/check-redundancy.py <file>
File: architecture.md
Lines: 89
Total phrases analyzed: 1247
Redundancy: 3.2%
✓ Redundancy optimal (3.2% ≤ 10%)
Or if redundancy is high:
File: verbose-file.md
Lines: 150
Total phrases analyzed: 2341
Redundancy: 15.8%
⚠️ High redundancy detected (15.8% > 10%)
Top repeated phrases:
- 'memory bank documentation' (12 times)
- 'project analysis json' (8 times)
- 'generation plan md' (7 times)
- 'static files to' (6 times)
- 'prompt templates in' (5 times)
After generating a file:
# Generate file
python generate-doc.py > .memory_bank/file.md
# Check redundancy
python ${CLAUDE_PLUGIN_ROOT}/skills/check-redundancy/scripts/check-redundancy.py .memory_bank/file.md
# If exit code is 1, optimize the file
if [ $? -eq 1 ]; then
echo "Optimizing file..."
# Run optimization
fi
for file in .memory_bank/**/*.md; do
python ${CLAUDE_PLUGIN_ROOT}/skills/check-redundancy/scripts/check-redundancy.py "$file"
done
/memento:optimize-memory-bank: Optimizes Memory Bank files with high redundancy/memento:fix-broken-links: Validates and fixes broken links in Memory Bank files.memory_bank/guides/code-review-guidelines.md: Documentation quality standardsnpx claudepluginhub mderk/memento --plugin mementoCompresses LLM-facing Markdown files like CLAUDE.md and ARCHITECTURE.md for token efficiency using lossless structural optimization or lossy semantic rewriting.
Detects AI-generated 'slop' markers like 'delve', 'tapestry', 'realm' in Markdown documentation and prose via vocabulary, structural patterns, and language detection. Flags density for cleanup and auditing.
Reviews documentation for data inconsistencies, broken references, typos, and unclear terminology. Use before publishing or committing to catch cross-file quality issues.